DevOps / MLOps Engineer

MacroCoderz; Pakistan; Remote; PKR 27,663,000 - 38,728,000; Full time

Job summary

MacroCoderz is seeking a fully remote DevOps / MLOps Engineer to manage cloud infrastructure, CI/CD pipelines, and monitoring for production AI systems. You will own environments across AWS, GCP and Azure, implement IaC, and ensure reliability, security and cost control for model endpoints and vector databases.

The role focuses on building pipelines, provisioning infrastructure as code, running containers in production, and setting up observability and cost-tracking for LLM workloads in a fully

Qualifications

• 3+ years running production workloads on AWS, GCP or Azure.
• Strong Linux, Docker and a CI/CD tool such as GitHub Actions or GitLab CI.
• Infrastructure as code with Terraform, Pulumi or similar.
• Scripting in Bash or Python.

Responsibilities

• Build and maintain CI/CD pipelines for application code, prompts and models.
• Provision cloud infrastructure as code.
• Run containers and services reliably in production.
• Set up monitoring, logging, alerting and LLM cost tracking.
• Apply security practices: secrets management, access control, backups and patching.

Skills

Linux

Docker

CI/CD

Bash

Python

Cloud platforms (AWS/GCP/Azure)

Tools

Terraform

Pulumi

GitHub Actions

GitLab CI

Job description

Remote DevOps / MLOps Engineer at MacroCoderz: run cloud infrastructure, CI/CD and monitoring for production AI systems, LLM services and vector databases.

AI systems bring infrastructure problems of their own: model endpoints with unpredictable latency, vector databases that grow fast, GPU workloads, and API bills that need watching. As a DevOps / MLOps Engineer you keep all of it reliable, secure and affordable.

You own environments across AWS, GCP and Azure, the pipelines that ship code and models, and the monitoring that tells us something is wrong before a client does.

What you will do

• Build and maintain CI/CD pipelines for application code, prompts and models.
• Provision cloud infrastructure as code.
• Run containers and services reliably in production.
• Set up monitoring, logging, alerting and LLM cost tracking.
• Apply security practices: secrets management, access control, backups and patching.

What we are looking for

• 3+ years running production workloads on AWS, GCP or Azure.
• Strong Linux, Docker and a CI/CD tool such as GitHub Actions or GitLab CI.
• Infrastructure as code with Terraform, Pulumi or similar.
• Scripting in Bash or Python.

Nice to have

• Kubernetes experience.
• Has deployed GPU workloads, model servers or vector databases.
• Observability tools such as Grafana, Prometheus or Datadog.

Location

fully remote, open to applicants worldwide.